This R Markdown script contains all the code used for outlier detection, data analysis and plotting; including additional statistical analyses and all the statistical models with summaries.
# Loading the data to filter out participants
dataExp1 <- read.delim("./dataAnonNotFilteredExp1_added.txt", sep ="\t", header = TRUE)
# Remove 11 suspicious participants
rmParticipant1Exp1 <- c("5970a90e","6e5ccd20","9e75832a","86687167","64afd2cc","429604bc","409f2599","d6390ddc","7ab6a320","bd90455b","39b29c2b")
dataExp1 <- dataExp1[!dataExp1$workerId %in% rmParticipant1Exp1,]
# Calculate dprime
# Get the hit rate: 4 or 5 to real words
dataExp1$accReal <- ifelse(dataExp1$type=="real" & dataExp1$enteredResponse %in% c(4,5),1,0)
hrateT <- aggregate(accReal ~ workerId, sum, data=dataExp1)
hrateT$hit_rate <- round(hrateT$accReal/132,3)
# Manually correct the hit rate of one participant (who did one less item)
#length(which(dataExp1$type=="real" & dataExp1$workerId=="c0999383"))
hrateT[hrateT$workerId=="c0999383",]$hit_rate <- round(hrateT[hrateT$workerId=="c0999383",]$accReal/131,3)
# Get the FA (false alarm) rate: 4-5 to nonwords
dataExp1$accNon <- ifelse(dataExp1$type=="non" & dataExp1$enteredResponse %in% c(4,5),1,0)
farateT <- aggregate(accNon ~ workerId, sum, data=dataExp1)
farateT$fa_rate <- round(farateT$accNon/209,3)
# Manually correct the FA rate of one participant (who did two less items)
#length(which(dataExp1$type=="non" & dataExp1$workerId=="f06d0f73"))
farateT[farateT$workerId=="f06d0f73",]$fa_rate <- round(farateT[farateT$workerId=="f06d0f73",]$accNon/207,3)
dprime <- merge(hrateT, farateT, by="workerId")
dprime$dprime <- round(qnorm(dprime$hit_rate) - qnorm(dprime$fa_rate),3)
dprime <- dprime[c("workerId","dprime")]
drop <- c("accReal","accNon")
dataExp1 <- dataExp1[,!(names(dataExp1) %in% drop)]
dataExp1 <- merge(dataExp1, dprime, by="workerId")
rm(dprime, hrateT, farateT)
# Remove 4 participants whose d-prime value is lower than 0
rmParticipant2Exp1 <- unique(dataExp1[dataExp1$dprime < 0,]$workerId)
# a29fe31d e1f518e6 efdd3439 f57a3633
dataExp1 <- dataExp1[!dataExp1$workerId %in% rmParticipant2Exp1,]
# Remove one native speaker of Mandarin Chinese
dataExp1 <- dataExp1[!dataExp1$firstLang=="Mandarin",]
# Remove 11 participants whose speakMaori or compMaori is equal to or above 3
rmParticipant3Exp1 <- unique(dataExp1[dataExp1$speakMaori >= 3 | dataExp1$compMaori >= 3,]$workerId)
# 007a1752 170ce007 20c10896 3128bb29 66d0a920 75caca3b b00cd565 d3cd7085 de95cdaf eef4d9c0 fab8a51f
dataExp1 <- dataExp1[!dataExp1$workerId %in% rmParticipant3Exp1,]
# Remove one participant who did not learn their English in NZ and have been living overseas for more than two years.
summaryExp1WorkerId <- unique(dataExp1[,c("workerId","firstLangCountry","place","duration")])
EngNotInNZExp1 <- summaryExp1WorkerId[!summaryExp1WorkerId$firstLangCountry=="NZ",]
rmParticipant4Exp1 <- unique(EngNotInNZExp1[EngNotInNZExp1$place=="overseas",]$workerId)
# 880242c2
dataExp1 <- dataExp1[!dataExp1$workerId %in% rmParticipant4Exp1,]
# Detect participant whose median reactionTime is shorter than 2*SD below the mean of all participants
median_RT <- aggregate(dataExp1$reactionTime, by=list(dataExp1$workerId), median)
names(median_RT) <- c("workerId","median")
cut <- mean(median_RT$median)-2*sd(median_RT$median)
# median_RT[!median_RT$median > cut,]$workerId # None detected!
# Check the total number of usable participants for Exp1
#length(unique(dataExp1$workerId)) # 101
The data is structured as follows:
Figure 1: Overview of participants’ sociolinguistic profile in Experiment 1. Bars are labeled with their counts for each category.
Figure 3: Length distribution of real word stimuli. The length of stimulus (the number of phonemes) is represented on the x-axis and the number of stimuli is represented on the y-axis.
Figure 4: Average word ratings by phonotactic score. Overlapping labels are not plotted.
Figure 4: Average word ratings by phonotactic score. Overlapping labels are not plotted.
Figure 4: Average word ratings by phonotactic score. Overlapping labels are not plotted.
# Model for Table 1
dataExp1DprimeFinite <- dataExp1[is.finite(dataExp1$dprime),]
dataExp1DprimeFinite$macron <- FALSE
dataExp1DprimeFinite[grepl("ā|ē|ī|ō|ū",dataExp1DprimeFinite$word),]$macron <- TRUE
dataExp1DprimeFinite$macron <- as.factor(dataExp1DprimeFinite$macron)
dataExp1DprimeFinite$enteredResponse <- as.factor(dataExp1DprimeFinite$enteredResponse)
# modelTable1 <- clmm(enteredResponse ~ macron*type*c.(dprime) + c.(n.neighbors)*type*c.(dprime) + c.(length)*c.(dprime) + c.(scoreDictToken) + (1 + macron*type + c.(n.neighbors)*type| workerId) + (1 + c.(length) + c.(scoreDictToken)| workerId) + (0 + c.(dprime)|word), data=dataExp1DprimeFinite)
# saveRDS(modelTable1, file = "modelTable1.rds")
modelTable1 <- readRDS("./modelTable1.rds")
clm_table(modelTable1, caption="Table 1: Model summary of confidence ratings with an ordinal mixed effects model. All numeric variables in this model are centered.")
| Parameter | Estimate | Std. Error | \(z\) | \(p\) | ||
|---|---|---|---|---|---|---|
| Effects | macron = TRUE | 1.043 | 0.073 | 14.291 | <0.001 | *** |
| type = real | 3.627 | 0.106 | 34.254 | <0.001 | *** | |
| dprime (centered) | -0.215 | 0.175 | -1.228 | 0.219 | ||
| n.neighbors (centered) | 0.034 | 0.004 | 8.364 | <0.001 | *** | |
| length (centered) | 0.045 | 0.011 | 3.953 | <0.001 | *** | |
| scoreDictToken (centered) | 0.977 | 0.060 | 16.372 | <0.001 | *** | |
| macron = TRUE × type = real | -0.478 | 0.086 | -5.545 | <0.001 | *** | |
| macron = TRUE × dprime (centered) | -0.628 | 0.132 | -4.741 | <0.001 | *** | |
| type = real × dprime (centered) | 1.489 | 0.173 | 8.610 | <0.001 | *** | |
| type = real × n.neighbors (centered) | -0.018 | 0.005 | -3.664 | <0.001 | *** | |
| dprime (centered) × n.neighbors (centered) | 0.018 | 0.010 | 1.776 | 0.076 | . | |
| dprime (centered) × length (centered) | -0.064 | 0.024 | -2.635 | 0.008 | ** | |
| macron = TRUE × type = real × dprime (centered) | 0.408 | 0.177 | 2.304 | 0.021 | * | |
| type = real × dprime (centered) × n.neighbors (centered) | -0.024 | 0.011 | -2.191 | 0.028 | * | |
| Thresholds | 1|2 | -2.800 | 0.115 | |||
| 2|3 | -0.611 | 0.113 | ||||
| 3|4 | 1.396 | 0.113 | ||||
| 4|5 | 2.668 | 0.114 |
Figure 5: Effect plots of the interaction between the presence of macrons and the distinction between non vs. real word stimuli on the top (Fig.5a), the interaction between the neighbourhood density and the distinction between non vs. real word stimuli on the middle (Fig.5b), the interaction between d′ and the presence of macrons (Fig.5c), and the frequency-weighted dictionary phonotactic score on the bottom (Fig.5d). Plots on the left show predicted mean ratings and plots on the right show predicted distributions over ratings.
# Model for Table S1
dataExp1DScore <- dataExp1DprimeFinite[dataExp1DprimeFinite$scoreDictToken > min(dataExp1DprimeFinite[dataExp1DprimeFinite$type=="real",]$scoreDictToken),]
# modelTableS1 <- clmm(enteredResponse ~ macron*type*c.(dprime) + c.(n.neighbors)*type*c.(dprime) + c.(length)*c.(dprime) + c.(scoreDictToken) + (1 + macron*type + c.(n.neighbors)*type| workerId) + (1 + c.(length) + c.(scoreDictToken)| workerId) + (0 + c.(dprime)|word), data=dataExp1DScore)
# saveRDS(modelTableS1, file = "modelTableS1.rds")
modelTableS1 <- readRDS("./modelTableS1.rds")
clm_table(modelTableS1, caption="Table S1: Model summary of confidence ratings with an ordinal mixed effects model with a subset of data after discarding 50 nonwords based on token-based dictionary phonotasctic scores. All numeric variables in this model are centered.")
| Parameter | Estimate | Std. Error | \(z\) | \(p\) | ||
|---|---|---|---|---|---|---|
| Effects | macron = TRUE | 0.969 | 0.077 | 12.566 | <0.001 | *** |
| type = real | 3.457 | 0.119 | 29.124 | <0.001 | *** | |
| dprime (centered) | -0.219 | 0.194 | -1.124 | 0.261 | ||
| n.neighbors (centered) | 0.026 | 0.005 | 5.675 | <0.001 | *** | |
| length (centered) | 0.033 | 0.013 | 2.605 | 0.009 | ** | |
| scoreDictToken (centered) | 1.319 | 0.079 | 16.780 | <0.001 | *** | |
| macron = TRUE × type = real | -0.540 | 0.093 | -5.788 | <0.001 | *** | |
| macron = TRUE × dprime (centered) | -0.678 | 0.146 | -4.644 | <0.001 | *** | |
| type = real × dprime (centered) | 1.530 | 0.196 | 7.811 | <0.001 | *** | |
| type = real × n.neighbors (centered) | -0.015 | 0.005 | -2.900 | 0.004 | ** | |
| dprime (centered) × n.neighbors (centered) | 0.019 | 0.011 | 1.702 | 0.089 | . | |
| dprime (centered) × length (centered) | -0.057 | 0.027 | -2.135 | 0.033 | * | |
| macron = TRUE × type = real × dprime (centered) | 0.384 | 0.193 | 1.995 | 0.046 | * | |
| type = real × dprime (centered) × n.neighbors (centered) | -0.024 | 0.012 | -2.091 | 0.037 | * | |
| Thresholds | 1|2 | -2.842 | 0.124 | |||
| 2|3 | -0.725 | 0.121 | ||||
| 3|4 | 1.240 | 0.121 | ||||
| 4|5 | 2.520 | 0.122 |
dataExp1$macron <- FALSE
dataExp1[grepl("ā|ē|ī|ō|ū",dataExp1$word),]$macron <- TRUE
dataExp1$macron <- as.factor(dataExp1$macron)
dataExp1$enteredResponse <- as.factor(dataExp1$enteredResponse)
# modelA <- clmm(enteredResponse ~ c.(scoreDictToken) + c.(n.neighbors) + macron + c.(length)*c.(maoriProf) + type*c.(maoriProf) + (1 + c.(scoreDictToken) + c.(n.neighbors) + macron | workerId) + (1 + c.(length) + type | workerId) + (0 + c.(maoriProf) | word), data=dataExp1)
# saveRDS(modelA, file = "modelA.rds")
modelA <- readRDS("./modelA.rds")
clm_table(modelA, caption="Table S2: Model summary of confidence ratings with an ordinal mixed effects model. All numeric variables in this model are centered.")
| Parameter | Estimate | Std. Error | \(z\) | \(p\) | ||
|---|---|---|---|---|---|---|
| Effects | scoreDictToken (centered) | 0.989 | 0.062 | 16.041 | <0.001 | *** |
| n.neighbors (centered) | 0.029 | 0.003 | 10.170 | <0.001 | *** | |
| macron = TRUE | 0.950 | 0.076 | 12.494 | <0.001 | *** | |
| length (centered) | 0.042 | 0.012 | 3.499 | <0.001 | *** | |
| maoriProf (centered) | -0.062 | 0.126 | -0.488 | 0.626 | ||
| type = real | 3.581 | 0.148 | 24.277 | <0.001 | *** | |
| length (centered) × maoriProf (centered) | -0.031 | 0.014 | -2.242 | 0.025 | * | |
| maoriProf (centered) × type = real | 0.520 | 0.180 | 2.895 | 0.004 | ** | |
| Thresholds | 1|2 | -2.769 | 0.116 | |||
| 2|3 | -0.642 | 0.113 | ||||
| 3|4 | 1.396 | 0.114 | ||||
| 4|5 | 2.662 | 0.114 |
Figure S1: Effect plots of phonotactic score (Fig.S1a) and neighbourhood density (Fig.S1b). Plots on the left show predicted mean ratings and plots on the right show predicted distributions over ratings.
# modelB <- clmm(enteredResponse ~ c.(scoreDictToken) + c.(n.neighbors) + macron + type + c.(length) + c.(maoriExpo) + (1 + c.(scoreDictType) + c.(n.neighbors) + macron | workerId) + (1 + type + c.(length) | workerId) + (0 + c.(maoriExpo) |word), data=dataExp1)
# saveRDS(modelB, file = "modelB.rds")
modelB <- readRDS("./modelB.rds")
clm_table(modelB, caption="Table S3: Model summary of confidence ratings with an ordinal mixed effects model. All numeric variables in this model are centered.")
| Parameter | Estimate | Std. Error | \(z\) | \(p\) | ||
|---|---|---|---|---|---|---|
| Effects | scoreDictToken (centered) | 0.937 | 0.051 | 18.427 | <0.001 | *** |
| n.neighbors (centered) | 0.029 | 0.003 | 9.753 | <0.001 | *** | |
| macron = TRUE | 0.838 | 0.075 | 11.186 | <0.001 | *** | |
| type = real | 3.566 | 0.152 | 23.435 | <0.001 | *** | |
| length (centered) | 0.039 | 0.012 | 3.281 | 0.001 | ** | |
| maoriExpo (centered) | 0.143 | 0.041 | 3.510 | <0.001 | *** | |
| Thresholds | 1|2 | -2.747 | 0.122 | |||
| 2|3 | -0.624 | 0.119 | ||||
| 3|4 | 1.412 | 0.120 | ||||
| 4|5 | 2.677 | 0.121 |
Figure S2: Effect plots of phonotactic score (Fig.S1a) and neighbourhood density (Fig.S1b). Plots on the left show predicted mean ratings and plots on the right show predicted distributions over ratings.
# modelC <- clmm(enteredResponse ~ c.(n.neighbors)*c.(scoreDictToken)*c.(maoriList) + type*c.(maoriList) + c.(length) + macron + (1 + c.(n.neighbors)*c.(scoreDictToken) + type | workerId) + (1 + c.(length) + macron | workerId) + (0 + c.(maoriList) | word), data=dataExp1)
# saveRDS(modelC, file = "modelC.rds")
modelC <- readRDS("./modelC.rds")
clm_table(modelC, caption="Table S4: Model summary of confidence ratings with an ordinal mixed effects model. All numeric variables in this model are centered.")
| Parameter | Estimate | Std. Error | \(z\) | \(p\) | ||
|---|---|---|---|---|---|---|
| Effects | n.neighbors (centered) | 0.027 | 0.003 | 8.527 | <0.001 | *** |
| scoreDictToken (centered) | 0.980 | 0.059 | 16.573 | <0.001 | *** | |
| maoriList (centered) | 0.065 | 0.045 | 1.423 | 0.155 | ||
| type = real | 3.605 | 0.133 | 27.030 | <0.001 | *** | |
| length (centered) | 0.043 | 0.012 | 3.648 | <0.001 | *** | |
| macron = TRUE | 0.949 | 0.076 | 12.442 | <0.001 | *** | |
| n.neighbors (centered) × scoreDictToken (centered) | 0.009 | 0.007 | 1.367 | 0.172 | ||
| n.neighbors (centered) × maoriList (centered) | 0.004 | 0.002 | 2.738 | 0.006 | ** | |
| scoreDictToken (centered) × maoriList (centered) | 0.013 | 0.034 | 0.386 | 0.700 | ||
| maoriList (centered) × type = real | 0.276 | 0.059 | 4.697 | <0.001 | *** | |
| n.neighbors (centered) × scoreDictToken (centered) × maoriList (centered) | -0.014 | 0.004 | -3.593 | <0.001 | *** | |
| Thresholds | 1|2 | -2.784 | 0.110 | |||
| 2|3 | -0.648 | 0.107 | ||||
| 3|4 | 1.405 | 0.108 | ||||
| 4|5 | 2.685 | 0.109 |
Figure S3: Effect plots of phonotactic score (Fig.S1a) and neighbourhood density (Fig.S1b). Plots on the left show predicted mean ratings and plots on the right show predicted distributions over ratings.
# Loading the data to filter out participants
dataExp2 <- read.delim("./dataAnonNotFilteredExp2_added.txt", sep ="\t", header = TRUE)
# Remove 9 participants whose speakMaori or compMaori is equal to or above 3
rmParticipant1Exp2 <- unique(dataExp2[dataExp2$speakMaori >= 3 | dataExp2$compMaori >= 3,]$workerId)
# 1b817b93 f44d2e0f 2d528dd7 90e5e8cd aa592fef a95bbe09 35ace421 b3f52c92 e7a6cb02
dataExp2 <- dataExp2[!dataExp2$workerId %in% rmParticipant1Exp2,]
# Remove one participant who did not learn their English in NZ and have been living overseas for more than two years (duration == "long")
summaryExp2WorkerId <- unique(dataExp2[,c("workerId","firstLangCountry","place","duration")])
EngNotInNZExp2 <- summaryExp2WorkerId[!summaryExp2WorkerId$firstLangCountry=="NZ",]
rmParticipant2Exp2 <- unique(EngNotInNZExp2[EngNotInNZExp2$place=="overseas",]$workerId)
# 1e48b18a
dataExp2 <- dataExp2[!dataExp2$workerId %in% rmParticipant2Exp2,]
# Detect participant whose median reactionTime is shorter than 2*SD below the mean of all participants
median_RT <- aggregate(dataExp2$reactionTime, by=list(dataExp2$workerId), median)
names(median_RT) <- c("workerId","median")
cut <- mean(median_RT$median)-2*sd(median_RT$median)
# median_RT[!median_RT$median > cut,]$workerId # None detected!
# Remove a participant with joke answers
dataExp2 <- dataExp2[!dataExp2$workerId=="eaed6b4d",]
# Check the total number of usable participants for Exp2
# length(unique(dataExp2$workerId)) # 123
The data is structured as follows:
Figure 2: Overview of participants’ sociolinguistic profile in Experiment 2. Bars are labeled with their counts for each category.
Figure 6: Rate of accurate definitions per word. Words are displayed according to their phonotactic score on the x-axis and their accuracy rates are represented on the y-axis. Phonotactic score is shown on the x-axis. Overlapping labels are not shown.
Figure 6: Rate of accurate definitions per word. Words are displayed according to their phonotactic score on the x-axis and their accuracy rates are represented on the y-axis. Phonotactic score is shown on the x-axis. Overlapping labels are not shown.
Figure 6: Rate of accurate definitions per word. Words are displayed according to their phonotactic score on the x-axis and their accuracy rates are represented on the y-axis. Phonotactic score is shown on the x-axis. Overlapping labels are not shown.
# Model for Table 2
# modelTable2 <- glmer(correct ~ c.(scoreRsSeg) + c.(familiarity) + c.(maoriList) + (1 + c.(scoreRsSeg) + c.(familiarity) |workerId) + (1+ c.(maoriList)|word), data=dataExp2, control=glmerControl(optimizer="bobyqa"), family=binomial(link="logit"))
# saveRDS(modelTable2, file = "modelTable2.rds")
modelTable2 <- readRDS("./modelTable2.rds")
kable(xtable(summary(modelTable2)$coef), digits=3, escape=F, full_width=T, caption="Table 2: Model summary for accuracy with a generalized linear mixed effects model. All numeric variables in this model are centered.")
| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 0.803 | 0.157 | 5.117 | 0.000 |
| c.(scoreRsSeg) | -1.569 | 0.716 | -2.191 | 0.028 |
| c.(familiarity) | 5.563 | 0.454 | 12.258 | 0.000 |
| c.(maoriList) | 0.461 | 0.042 | 10.844 | 0.000 |
Figure 7: Effect plot of phonotactic score on accuracy.
# Model for Table S5 (Māori proficiency)
# modelTableS5 <- glmer(correct ~ c.(scoreRsSeg) + c.(familiarity) + c.(maoriProf) + (1 + c.(scoreRsSeg) + c.(familiarity) |workerId) + (1+ c.(maoriProf)|word), data=dataExp2, control=glmerControl(optimizer="bobyqa"), family=binomial(link="logit"))
# saveRDS(modelTableS5, file = "modelTableS5.rds")
modelTableS5 <- readRDS("./modelTableS5.rds")
kable(xtable(summary(modelTableS5)$coef), digits=3, caption="Table S5 (Māori proficiency): Modeling summary for accuracy with a generalized linear mixed effects model. All numeric variables in this model are centered.")
| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 0.742 | 0.169 | 4.388 | 0.000 |
| c.(scoreRsSeg) | -1.423 | 0.714 | -1.992 | 0.046 |
| c.(familiarity) | 5.213 | 0.457 | 11.400 | 0.000 |
| c.(maoriProf) | 0.725 | 0.125 | 5.804 | 0.000 |
# Model for Table S6 (Exposure to Māori)
# modelTableS6 <- glmer(correct ~ c.(scoreRsSeg) + c.(familiarity) + c.(maoriExpo) + (1 + c.(scoreRsSeg) + c.(familiarity) |workerId) + (1+ c.(maoriExpo)|word), data=dataExp2, control=glmerControl(optimizer="bobyqa"), family=binomial(link="logit"))
# saveRDS(modelTableS6, file = "modelTableS6.rds")
modelTableS6 <- readRDS("./modelTableS6.rds")
kable(xtable(summary(modelTableS6)$coef), digits=3, caption="Table S6 (Exposure to Māori): Modeling summary for accuracy with a generalized linear mixed effects model. All numeric variables in this model are centered.")
| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 0.743 | 0.165 | 4.503 | 0.000 |
| c.(scoreRsSeg) | -1.889 | 0.678 | -2.786 | 0.005 |
| c.(familiarity) | 5.037 | 0.431 | 11.682 | 0.000 |
| c.(maoriExpo) | 0.388 | 0.052 | 7.397 | 0.000 |
# Model for Figure 8
# modelFigure8 <- glmer(correct ~ c.(scoreDictToken) + c.(n.neighbors) + c.(familiarity) + c.(maoriList) + (1 + c.(scoreDictToken) + c.(familiarity)|workerId) + (0 + c.(n.neighbors)|workerId) + (1 + c.(maoriList)|word), data=dataExp2, control=glmerControl(optimizer="bobyqa"), family=binomial(link="logit"))
# saveRDS(modelFigure8, file = "modelFigure8.rds")
modelFigure8 <- readRDS("./modelFigure8.rds")
kable(xtable(summary(modelFigure8)$coef), digits=3, caption="Table S7: Model summary for accuracy with a generalized linear mixed effects model. All numeric variables in this model are centered.")
| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 0.816 | 0.158 | 5.148 | 0.00 |
| c.(scoreDictToken) | -1.019 | 0.708 | -1.438 | 0.15 |
| c.(n.neighbors) | 0.027 | 0.014 | 1.964 | 0.05 |
| c.(familiarity) | 5.589 | 0.460 | 12.156 | 0.00 |
| c.(maoriList) | 0.468 | 0.043 | 10.804 | 0.00 |
Figure 8: Effect plot of neighbourhood density on accuracy.
How well are you able to speak Māori?
\(\square\) Very well (I can talk about almost anything in Māori)
\(\square\) Well (I can talk about many things in Māori)
\(\square\) Fairly well (I can talk about some things in Māori)
\(\square\) Not very well (I can only talk about simple/basic things in Māori)
\(\square\) No more than a few words or phrases
\(\square\) Not at all
How well are you able to understand/read Māori?
\(\square\) Very well (I can understand almost anything said/written in Māori)
\(\square\) Well (I can understand many things said/written in Māori)
\(\square\) Fairly well (I can understand some things said/written in Māori
\(\square\) Not very well (I can only understand simple/basic things said/written in Māori)
\(\square\) No more than a few words or phrases
\(\square\) Not at all
Which age group do you belong to?
\(\square\) 18 - 29
\(\square\) 30 - 39
\(\square\) 40 - 49
\(\square\) 50 - 59
\(\square\) +60
Please state your gender:
Please state your ethnicity:
Your highest education is:
\(\square\) High school
\(\square\) Undergraduate degree
\(\square\) Graduate degree
How often do you think you are exposed to the Māori language in your daily life, by means of Māori radio, Māori TV, online media?
\(\square\) Less than once a year
\(\square\) Less than once a month
\(\square\) Less than once a week
\(\square\) Less than once a day
\(\square\) Multiple times a day
How often do you think you are exposed to Māori language in your daily life, in conversation at work, at home, in social settings?
\(\square\) Less than once a year
\(\square\) Less than once a month
\(\square\) Less than once a week
\(\square\) Less than once a day
\(\square\) Multiple times a day
In the past five years, have you had any children living with you who have attended preschool or primary school in New Zealand?
\(\square\) Yes
\(\square\) No
Please tick all boxes that apply.
\(\square\) I can give a mihi in Māori.
\(\square\) I can sing a few songs in Māori.
\(\square\) I can sing the NZ national anthem in Māori.
\(\square\) I know how to say some basic phrases (e.g. My name is…, I’m from…) in Māori.
\(\square\) I know how to say some commands (e.g. Sit down / Come here) in Māori.
\(\square\) I know how to say some greetings in Māori.
\(\square\) I know how to say some numbers in Māori.
\(\square\) I know how to say some body parts in Māori.
\(\square\) I know how to say some colors in Māori.
What region of New Zealand do you live in currently? (Please choose ``overseas" if you are living outside of New Zealand.)
\(\square\) Northland
\(\square\) Auckland
\(\square\) Waikato
\(\square\) Bay of Plenty
\(\square\) Gisborne
\(\square\) Hawke’s Bay
\(\square\) Taranaki
\(\square\) Wanganui
\(\square\) Manawatu
\(\square\) Wairarapa
\(\square\) Wellington
\(\square\) Nelson Bays
\(\square\) Marlborough
\(\square\) West Coast
\(\square\) Canterbury
\(\square\) Timaru - Oamaru
\(\square\) Otago
\(\square\) Southland
\(\square\) Overseas
How long have you been living there?
Please state your first language (the language you speak/use most of your time).
What country were you living in when you first learned this language?
Please list any other languages that you can speak fluently:
Have you ever lived in Hawaii?
\(\square\) Yes
\(\square\) No
Do you speak/understand any Polynesian languages such as Hawaiian, Tahitian, Sāmoan, or Tongan?
\(\square\) Yes
\(\square\) No
If you replied yes to question 17, please state the language you know.
Do you have a history of any speech or language impairments that you are aware of?
\(\square\) Yes \(\square\) No
realword <- dataExp1[dataExp1$type=="real",]
listword <- paste(unique(realword$word), collapse=", ")
kable(listword, caption="Table 4: List of stimuli for Experiment 1 - real words",col.names = NULL)
| karakia, tangi, pākehā, papa, haere mai, rua, manuhiri, rangatira, taringa, whāngai, māori, kaha, waru, karanga, reo, waewae, tupuna, mahi, ringaringa, whero, ora, iwi, papatūānuku, karu, motu, waha, taiaha, mauī, kahurangi, pokohiwi, awa, hoki, hope, atua, tekau, kaupapa, turituri, ako, toru, korowai, mokopuna, hongi, waiata, taihoa, kai moana, tiki, mihi, whakarongo, kākāriki, puke, koro, iti, rangatiratanga, whenua, waka, tāne, katoa, aoraki, moana, kaitiaki, wahine, kurī, mana, kura, taonga, poi, marae, kapa haka, tāngata, aroha, tēnā koe, ranginui, whanau, pounamu, iwa, ihu, mōrena, puku, mate, ono, hui, maunga, whare, tuakana, wāhi tapu, mere, wai, taniwha, hīkoi, hōhā, matariki, moko, tapu, whitu, hangi, nui, kōhanga, tangata whenua, māwhero, noho, tohunga, kāwanatanga, hapū, haka, wānanga, whaea, teina, kia ora, kuia, kōrero, aotearoa, pai, roto, utu, rima, kia kaha, koru, tamariki, pango, pōwhiri, tahi, kāinga, kai, rangi, whakapapa, upoko, kaiwhakahaere, tikanga, tēnā koutou, kōwhai, kaumātua, koha |
pseudoword <- dataExp1[dataExp1$type=="non",]
listword <- paste(unique(pseudoword$word), collapse=", ")
kable(listword, caption="Table 5: List of stimuli for Experiment 1 - nonwords",col.names = NULL)
| māheneketoa, pukau nia, pikeko, pūrawha, titapa, huengi, pie, kepi, ape, hakaatū, ikau, rumo, tawhengawhi, mautāmu, nia, mihea, taetū, wereu, whani nia, tuwhe, pūno, mango, whenepōna, pūwhi, rahue, teu, kawaa, ahiahake, pūtio, eko, nia whihia, kūhatapō, ahatiati, moapi, kāweroni, tāmarutō, inga, mero, takamīa, howaka, hoihoko, temi, ngawhāniti, tūkeiati, whuri, ngapoto, teaori, rupo, whataī, wheu, tīahu, pahapā, kūro, hōke, nito, mōnga, nia pukau, tikaweneri, tārorangī, nia ire, hunge, moeo, tumeiroruare, mōha, komekua, mie, tākapī, poraki, kupō, kawha, ngue, pukau, taongirua, kōua, tie, amu, whani kawha, whani whani, ngoa, nitumaotaha, tītā, ngepa, kingiro, rūne, ngehi, māwi, hāno, hiu, pāwhi, tāhuma, eha, ingi, māorawau, kitō, arane, hewe, nōitia, hepiti, meahua, nia whani, nuti, paihoui, wikuruta, whihia nia, whaha, tetoua, rowa, nguta, pīhu, nue, wuri, rangu, tohiāhia, mamatōhī, mupati, tatūhe, ngae, ngaena, tikōha, apēhia, pīngi, humo, haeo, hingi, horetī, whāngaki, toketi, nia kawha, whihia, wehao, wheto, wura, puora, hupū, hiamu, uke, makei, uro, waemura, rungu, peu, nure, kōmuawhiu, pāuki, iko, rowhaohi, pāhāpāko, tetohe, whāhu, whengo, natoi, kemoramo, whani, kawha whani, tīkīhiki, nuhi, neetia, uti, pewe, reru, whani poraki, whakōiaweahua, ire, tīpe, kōioromāpara, kawha nia, nia uti, mungi, iniata, tapopa, rupa, hoengaima, rukō, ario, unati, pume, naipu, kawha kawha, nema, ngemetata, whutarirari, iru, whaiē, hūku, tikū, nopo, māorua, rume, tuanapū, pote, tīpo, paurounu, mini, ihiri, hepaua, whani titapa, nānga, kūwhati, rapeia, whehu, ino, ngema, tiwhi, uko, wawemiti, rapuko, titapa pukau, poraki pukau, touki |
listword <- paste(unique(dataExp2$word), collapse=", ")
kable(listword, caption="Table 6: List of stimuli for Experiment 2",col.names = NULL)
| aoraki, aroha, atua, awa, whaea, whakapapa, whakarongo, whāngai, whanau, whare, whenua, whero, whitu, haere mai, haka, hangi, hapū, hīkoi, hōhā, hoki, hongi, hui, iti, iwa, iwi, kaha, kahurangi, kai, kai moana, kāinga, kaitiaki, kākāriki, kapa haka, karakia, karanga, katoa, kaumātua, kaupapa, kāwanatanga, kia kaha, kia ora, kōwhai, koha, kōhanga, kōrero, koro, korowai, koru, kuia, kura, kurī, māwhero, mahi, mana, manuhiri, marae, matariki, mauī, maunga, mere, mihi, moana, moko, mokopuna, mōrena, motu, noho, nui, ono, ora, pai, papa, papatūānuku, pōwhiri, poi, pounamu, puke, puku, rangatira, rangatiratanga, rangi, ranginui, reo, rima, ringaringa, roto, rua, tahi, taiaha, taihoa, tamariki, tāngata, tangata whenua, tāne, tangi, taniwha, taonga, tapu, taringa, teina, tekau, tēnā koe, tēnā koutou, tikanga, tiki, tohunga, toru, tuakana, tupuna, utu, waewae, wahine, wāhi tapu, wai, waiata, waka, wānanga, waru |